COVID-19 Progression: Australian Data Only

library(tidyverse)
library(magrittr)
library(lubridate)
library(scales)
library(matrixStats)
library(ggrepel)
library(broom)
library(glue)
library(jsonlite)
library(rvest)
library(RCurl)
library(pander)
library(plotly)
library(cowplot)
library(QuantTools)
library(ggfortify)
library(readxl)
library(httr)
panderOptions("big.mark", ",")
panderOptions("table.split.table", Inf)
panderOptions("table.style", "rmarkdown")
panderOptions("missing", "")
theme_set(theme_bw())

auStates <- c(
  ACT = "Australian Capital Territory",
  QLD = "Queensland",
  NSW = "New South Wales",
  VIC = "Victoria",
  SA = "South Australia",
  WA = "Western Australia",
  NT = "Northern Territory",
  TAS = "Tasmania"
)

Data Sources

getConfirmed <- function(state, .state_full = auStates){
  state <- str_to_lower(state)
  url <- glue("https://covidlive.com.au/report/daily-cases/{state}")
  url %>%
    read_html() %>%
    html_nodes("body") %>%
    xml_find_all("//table[contains(@class, 'DAILY-CASES')]") %>% 
    html_table() %>%
    .[[1]] %>%
    as_tibble() %>%
    dplyr::select(date = DATE, confirmed = CASES) %>%
    separate(date, into = c("day", "month")) %>%
    mutate(
      year = year(today()),
      date = paste(year, month, day, sep = "-"),
      date = parse_date_time(date, orders = "%Y-%B-%d"),
      date = ymd(date),
      confirmed = str_remove_all(confirmed, ","),
      confirmed = as.numeric(confirmed),
      State = .state_full[str_to_upper(state)],
      Country = "Australia"
    ) %>%
    dplyr::select(State, Country, date, confirmed) %>%
    arrange(date) 
}
confirmed <- names(auStates) %>%
  lapply(getConfirmed) %>%
  bind_rows()

getRecovered <- function(state, .state_full = auStates){
  state <- str_to_lower(state)
  url <- glue("https://covidlive.com.au/report/daily-recoveries/{state}")
  url %>%
    read_html() %>%
    html_nodes("body") %>%
    xml_find_all("//table[contains(@class, 'DAILY-RECOVERIES')]") %>% 
    html_table() %>%
    .[[1]] %>%
    as_tibble() %>%
    dplyr::select(date = DATE, recovered = RECOV) %>%
    separate(date, into = c("day", "month")) %>%
    mutate(
      year = year(today()),
      date = paste(year, month, day, sep = "-"),
      date = parse_date_time(date, orders = "%Y-%B-%d"),
      date = ymd(date),
      recovered = str_remove_all(recovered, ","),
      recovered = as.numeric(recovered),
      State = .state_full[str_to_upper(state)],
      Country = "Australia"
    ) %>%
    dplyr::select(State, Country, date, recovered) %>%
    arrange(date) 
}
recovered <- names(auStates) %>%
  lapply(getRecovered) %>%
  bind_rows()

getDeaths <- function(state, .state_full = auStates){
  state <- str_to_lower(state)
  url <- glue("https://covidlive.com.au/report/daily-deaths/{state}")
  url %>%
    read_html() %>%
    html_nodes("body") %>%
    xml_find_all("//table[contains(@class, 'DAILY-DEATHS')]") %>% 
    html_table() %>%
    .[[1]] %>%
    as_tibble() %>%
    dplyr::select(date = DATE, deaths = DEATHS) %>%
    separate(date, into = c("day", "month")) %>%
    mutate(
      year = year(today()),
      date = paste(year, month, day, sep = "-"),
      date = parse_date_time(date, orders = "%Y-%B-%d"),
      date = ymd(date),
      deaths = str_remove_all(deaths, ","),
      deaths = as.numeric(deaths),
      State = .state_full[str_to_upper(state)],
      Country = "Australia"
    ) %>%
    dplyr::select(State, Country, date, deaths) %>%
    arrange(date) 
}
deaths <- names(auStates) %>%
  lapply(getDeaths) %>%
  bind_rows()

getActive <- function(state, .state_full = auStates){
  state <- str_to_lower(state)
  url <- glue("https://covidlive.com.au/report/daily-active-cases/{state}")
  url %>%
    read_html() %>%
    html_nodes("body") %>%
    xml_find_all("//table[contains(@class, 'DAILY-ACTIVE-CASES')]") %>% 
    html_table() %>%
    .[[1]] %>%
    as_tibble() %>%
    dplyr::select(date = DATE, active = ACTIVE) %>%
    separate(date, into = c("day", "month")) %>%
    mutate(
      year = year(today()),
      date = paste(year, month, day, sep = "-"),
      date = parse_date_time(date, orders = "%Y-%B-%d"),
      date = ymd(date),
      active = str_remove_all(active, ","),
      active = as.numeric(active),
      State = .state_full[str_to_upper(state)],
      Country = "Australia"
    ) %>%
    dplyr::select(State, Country, date, active) %>%
    arrange(date) 
}
active <- names(auStates) %>%
  lapply(getActive) %>%
  bind_rows()

getTested <- function(state, .state_full = auStates){
  state <- str_to_lower(state)
  url <- glue("https://covidlive.com.au/report/daily-tests/{state}")
  url %>%
    read_html() %>%
    html_nodes("body") %>%
    xml_find_all("//table[contains(@class, 'DAILY-TESTS')]") %>% 
    html_table() %>%
    .[[1]] %>%
    as_tibble() %>%
    dplyr::select(date = DATE, tests = TESTS) %>%
    separate(date, into = c("day", "month")) %>%
    mutate(
      year = year(today()),
      date = paste(year, month, day, sep = "-"),
      date = parse_date_time(date, orders = "%Y-%B-%d"),
      date = ymd(date),
      tests = str_remove_all(tests, ","),
      tests = as.numeric(tests),
      State = .state_full[str_to_upper(state)],
      Country = "Australia"
    ) %>%
    dplyr::select(State, Country, date, tests) %>%
    arrange(date) 
}
tested <- names(auStates) %>%
  lapply(getTested) %>%
  bind_rows() %>%
  dplyr::filter(!is.na(tests))

Data for confirmed cases, active cases, recoveries and fatalities was exclusively sourced from COVID LIVE.

International Data

International data and figures can be viewed here

dt <- max(confirmed$date)
dt_char <- as.character(dt)

Latest Australian Data

ausPops <- tribble(
  ~State, ~Population,
  "New South Wales",    8117976,
  "Victoria", 6629870,
  "Queensland", 5115451,
  "South Australia", 1756494,
  "Western Australia", 2630557,
  "Tasmania", 535500,
  "Northern Territory", 245562,
  "Australian Capital Territory", 428060
)

Australian State populations were taken from the ABS Website and were accurate in Sept 2019.

• Using an estimated population size of 25,459,470, the total percentage of the Australian population confirmed as having been infected currently sits at 0.11%, or one person in every 903.
• Within Victoria, that rises to one in every 326 having contracted the virus at some point

confirmed %>% 
  left_join(recovered) %>%
  left_join(deaths) %>%
  left_join(active) %>%
  dplyr::filter(
    date >= max(date) - 1
  ) %>%
  group_by(State) %>%
  mutate(
    Increase = c(NA, diff(confirmed)),
    `% Increase` = Increase / min(confirmed),
    recovered = c(NA, max(recovered)),
    deaths = c(NA, max(deaths)),
    active = c(NA, active[2])
  ) %>%
  ungroup() %>%
  pivot_wider(
    id_cols = State, 
    names_from = date, 
    values_from = c(confirmed, recovered, deaths, active, Increase, `% Increase`)
  ) %>%
  dplyr::select_if(function(x){sum(is.na(x)) <= 1}) %>%
  rename_all(
    str_remove_all, pattern = "confirmed_"
  ) %>%
  rename_all(str_remove_all, pattern = "_202[01].+") %>%
  bind_rows(
    tibble(
      State = "National Total",
      "{as.character(dt -1)}" := sum(.[[as.character(dt -1)]]),
      "{dt_char}" := sum(.[[dt_char]]),
      Increase = sum(.$Increase),
      recovered = sum(.$recovered),
      deaths = sum(.$deaths),
      active = sum(.$active),
      `% Increase` = Increase / !!sym(as.character(dt - 1))
    )
  ) %>%
  mutate(
    `% Increase` = percent(`% Increase`, accuracy = 0.01),
    `Fatality Rate` = percent(deaths / !!sym(dt_char), accuracy = 0.1),
    `Recovery Rate` = percent(recovered / !!sym(dt_char), accuracy = 0.1),
  ) %>%
  rename(
    Fatalities = deaths,
    Recovered = recovered,
    `Currently Active` = active
  ) %>%
  dplyr::select(
    State, starts_with("20"), ends_with("Increase"), starts_with("Fatal"), starts_with("Recov"), `Currently Active`
  ) %>%
  pander(
    justify = "lrrrrrrrrr",
    caption = paste(
      "*Confirmed cases, fatalities and recoveries reported by each state at time of preparation.",
      "Any states with unchanged, or decreasing confirmed cases may indicate delays with the automated data sources, such as health.gov.au or JHU, or that these states have not yet reported for the day.", 
      "Please note that some discrepancy with dates may occur due to automated data sources obtained different time zones, such as the USA, the UK and Australia.*"
    ),
    emphasize.strong.rows = nrow(.)
  )

Joining, by = c(“State”, “Country”, “date”) Joining, by = c(“State”, “Country”, “date”) Joining, by = c(“State”, “Country”, “date”)

Confirmed cases, fatalities and recoveries reported by each state at time of preparation. Any states with unchanged, or decreasing confirmed cases may indicate delays with the automated data sources, such as health.gov.au or JHU, or that these states have not yet reported for the day. Please note that some discrepancy with dates may occur due to automated data sources obtained different time zones, such as the USA, the UK and Australia.

State	2020-12-20	2020-12-21	Increase	% Increase	Fatalities	Fatality Rate	Recovered	Recovery Rate	Currently Active
Australian Capital Territory	118	118	0	0.00%	3	2.5%	114	96.6%	1
Queensland	1,234	1,235	1	0.08%	6	0.5%	1,214	98.3%	10
New South Wales	4,748	4,771	23	0.48%	53	1.1%	3,192	66.9%	87
Victoria	20,356	20,357	1	0.00%	820	4.0%	19,524	95.9%	13
South Australia	566	566	0	0.00%	4	0.7%	559	98.8%	3
Western Australia	845	846	1	0.12%	9	1.1%	826	97.6%	11
Northern Territory	71	71	0	0.00%	0	0.0%	59	83.1%	12
Tasmania	234	234	0	0.00%	13	5.6%	221	94.4%	0
National Total	28,172	28,198	26	0.09%	908	3.2%	25,709	91.2%	137

Plot of Current Australian Values

ausStatsCap <- "*Current confirmed and recovered cases, along with fatalities for Australia only. Active cases are shown as confirmed cases excluding fatalities and those classed as recovered. Loess curves through all points are shown as continuous lines. Data is only shown from 1^st^ April 2020 as this was the first date of complete data being available. Recovered patient information was also sparse in the early stages of data collection, and as a result estimates of active infections will be a significant underestimate until 6^th^ April. In particular, QLD only began reporting recovered cases on this date. NSW followed a fortnight after this date and as such, only the most recent numbers can be considered as accurate. Below this plot, the same figures can be seen broken down by state.*"

ggplotly(
  confirmed %>%
    left_join(deaths) %>%
    left_join(recovered) %>%
    left_join(active) %>%
    mutate_at(vars(confirmed, deaths, recovered, active), na_locf) %>%
    group_by(Country, date) %>%
    summarise_at(vars(confirmed, deaths, recovered, active), sum) %>%
    ungroup() %>%
    pivot_longer(
      cols = c(active, confirmed, deaths, recovered),
      names_to = "Status",
      values_to = "Total"
    ) %>%
    arrange(Status, date) %>%
    dplyr::filter(date > ymd("2020-04-01")) %>%
    mutate(
      Status = str_to_title(Status),
      Status = str_replace_all(Status, "Deaths", "Fatal"),
      Status = factor(Status, levels = c("Fatal", "Recovered", "Active"))
    ) %>%
    dplyr::filter(Total > 0) %>%
    rename_all(str_to_title) %>%
    dplyr::filter(Status != "Confirmed") %>%
    ggplot(aes(Date, Total, fill = Status)) +
    geom_col() +
    geom_line(
      data = . %>%
        group_by(Date) %>%
        summarise(
          Total = sum(Total)
        ) %>%
        mutate(Status = "Confirmed"),
      colour = "blue"
    ) +
    scale_fill_manual(
      values = c(
        Active = rgb(0, 0, 0),
        Confirmed = rgb(0, 0.3, 0.7),
        Fatal = rgb(0.8, 0.2, 0.2),
        Recovered = rgb(0.2, 0.7, 0.4)
      )
    ) +
    scale_x_date(expand = expansion(c(0, 0.03))) +
    scale_y_continuous(expand = expansion(c(0, 0.05))) +
    labs("Total Cases")
)

Current confirmed and recovered cases, along with fatalities for Australia only. Active cases are shown as confirmed cases excluding fatalities and those classed as recovered. Loess curves through all points are shown as continuous lines. Data is only shown from 1^st April 2020 as this was the first date of complete data being available. Recovered patient information was also sparse in the early stages of data collection, and as a result estimates of active infections will be a significant underestimate until 6^th April. In particular, QLD only began reporting recovered cases on this date. NSW followed a fortnight after this date and as such, only the most recent numbers can be considered as accurate. Below this plot, the same figures can be seen broken down by state.

ggplotly(
  confirmed %>%
    left_join(deaths) %>%
    left_join(recovered) %>%
    left_join(active) %>%
    mutate_at(vars(confirmed, deaths, recovered, active), na_locf) %>%
    dplyr::filter(
      date > ymd("2020-04-01"),
    ) %>%
    arrange(date) %>%
    left_join(ausPops) %>%
    pivot_longer(
      cols = c(confirmed, deaths, recovered, active),
      names_to = "status",
      values_to = "count"
    ) %>%
    dplyr::filter(
      count > 0,
      !(State %in% c("Queensland", "New South Wales") & status == "recovered" & date < ymd("2020-04-06")),
      !(State %in% c("South Australia") & status == "recovered" & date < ymd("2020-04-01")),    
      !(State %in% c("Tasmania") & status == "recovered" & date < ymd("2020-04-02")),
    ) %>%
    dplyr::filter(status != "confirmed") %>%
    mutate(
      rate = 1e6*count/Population,
      rate = round(rate, 2),
      status = str_replace(status, "deaths", "fatal") %>% str_to_title(),
      status = factor(status, levels = c("Fatal", "Recovered", "Active"))
    ) %>%
    rename_all(str_to_title) %>%
    ggplot(aes(Date, Rate, fill = Status, label = Count)) +
    geom_col() +
    geom_line(
      data = . %>%
        group_by(State, Date) %>%
        summarise(
          Rate = sum(Rate),
          Count = sum(Count)
        ) %>%
        mutate(Status = "Confirmed"),
      colour = "blue"
    ) +
    facet_wrap(~State, ncol = 4) + 
    scale_fill_manual(
      values = c(
        Active = rgb(0, 0, 0),
        Confirmed = rgb(0, 0.3, 0.7),
        Fatal = rgb(0.8, 0.2, 0.2),
        Recovered = rgb(0.2, 0.7, 0.4)
      )
    ) +
    scale_x_date(expand = expansion(c(0, 0.03))) +
    labs(y = "Rate (Cases / Million)")
)

Breakdown of individual states. Victorian recovered numbers began to be accurately reported from 22^nd March, with other states gradually providing this information. NSW/QLD recovered cases have only recently begun being reported and up until the most recent dates, recovered/active values were very approximate for these states. The extreme drop for NSW active cases in early June is a function of the changed reporting strategy implemented by NSW Health.

Daily New Cases

ggplotly(
  confirmed %>%
    group_by(State) %>%
    mutate(daily = c(0, diff(confirmed))) %>%
    ungroup() %>%
    dplyr::filter(confirmed > 0) %>%
    mutate(
      daily = case_when(
        daily < 0 ~ 0,
        daily >= 0 ~ daily
      )
    ) %>%
    bind_rows(
      group_by(., date) %>%
        summarise(daily = sum(daily)) %>%
        ungroup() %>%
        mutate(State = "All States")
    ) %>%
    group_by(State) %>%
    mutate(
      MA = round(sma(daily, 7), 2),
      MA2 = round(sma(daily, 14), 2),
      `Above Average` = MA > MA2
    ) %>%
    dplyr::filter(date > "2020-03-01") %>%
    ggplot(aes(date, daily)) +
    geom_col(
      aes(fill = `Above Average`, colour = `Above Average`),
      data = . %>% dplyr::filter(!is.na(`Above Average`)),
      width = 1/2
    ) +
    geom_line(aes(y = MA), colour = "blue") +
    geom_line(aes(y = MA2), colour = "black") +
    facet_wrap(~State, scales = "free_y") +
    labs(
      x = "Date",
      y = "Daily New Cases",
      fill = "\nAbove\nAverage"
    ) +
    scale_fill_manual(values = c("white", rgb(1, 0.2, 0.2))) +
    scale_colour_manual(values = c("grey50", rgb(1, 0.2, 0.2))),
  tooltip = c(
    "date", "daily", "MA"
  )
)

Daily new cases for each state shown against the 7-day (blue) and 14-day (black) averages. Days which the 7-day average is above the 14-day average are highlighted in red.

Australian Fatality Rate

inc <- 6
icu <- 11
d <- 7
offset <- icu + d 
minDate <- "2020-04-20"

list(
  confirmed %>%
    group_by(date) %>%
    summarise_at("confirmed", sum) %>%
    left_join(
      deaths %>%
        group_by(date) %>%
        summarise_at("deaths", sum) 
    ) %>%
    dplyr::filter(
      date > minDate
    ) %>%
    mutate(
      fr = deaths / confirmed,
      type = "No Offset"
    ),
  confirmed %>%
    mutate(
      date = date + offset 
    ) %>%
    group_by(date) %>%
    summarise_at("confirmed", sum) %>%
    left_join(
      deaths %>%
        group_by(date) %>%
        summarise_at("deaths", sum) 
    ) %>%
    dplyr::filter(
      date > minDate
    ) %>%
    mutate(
      fr = deaths / confirmed,
      type = glue("Offset ({offset} days)")
    ) 
) %>%
  bind_rows() %>%
  ggplot(
    aes(date, fr, colour = type)
  ) +
  geom_line() +
  scale_x_date(
    expand = expansion(mult = 0, add = 0)
  ) +
  scale_y_continuous(label = percent) +
  labs(
    x = "Date",
    y = "Estimated Fatality Rate",
    colour = "Calculation"
  )

Fatality rate for Australian cases as calculated using two methods. Where no offset is included, the rate shown is simply the number of fatalities divided by the total number of reported cases on the same date. When cases increase during a new outbreak, this will skew the fatality rate lower. An alternative is to use an offset based on the fact the the median time from infection to symptom onset is 6 days, the median time from symptom onset to ICU admission is 11 days, and the median time from ICU admission to mortality is 7 days. When using the offset, the fatality rate is calculated as the number of recorded fatalities on a given date, divided by by the number of cases from 18 days ago. Whilst still flawed this may give a less biased estimate on the true fatality rate, and importantly, will always be higher than the alternative calculation. The intial fatality rate spiked above 30% during the intial outbreak under the offset approach, and as such, data is only shown after 20 Apr, 2020. All times used for estimation the offset were obtained from here

Current Growth Factor

n <- 14
cp <- glue(
  "*Growth factor for each State/Territory. 
  This value becomes volatile when daily new cases approach zero as is commonly observed in small populations, and at the end stages of an outbreak. 
  Given the multiple updates during the course of the day, values shown represent those up to the previous day.
  In order to try and minimise volatility a {n} day simple moving average was used, in contrast to the 5 day average as advocated [here](https://www.abc.net.au/news/2020-04-10/coronavirus-data-australia-growth-factor-covid-19/12132478).
  This enables assessment of the growth factor over an entire quarantine period.
  If no new cases are observed over this period, the value is not able to be calculated.
  The dashed vertical lines indicate the day most state borders were closed.*"
)

gf <- list(
  confirmed %>%
    dplyr::filter(Country == "Australia", date < dt) %>%
    arrange(date) %>%
    group_by(State) %>%
    mutate(
      new = c(0, diff(confirmed)),
      new_ma = sma(new, n)
    ) %>%
    dplyr::filter(confirmed > 0, !is.na(new_ma)) %>%
    mutate(
      R = c(NA, new_ma[-1] / new_ma[-n()]),
      R = case_when(
        is.nan(R) ~ NA_real_,
        !is.nan(R) ~ R
      )
    ) %>%
    ungroup() %>%
    arrange(State),
  confirmed %>%
    dplyr::filter(Country == "Australia", date < dt) %>%
    arrange(date) %>%
    group_by(Country, date) %>%
    summarise_at(vars(confirmed), sum) %>%
    ungroup() %>%
    mutate(
      new = c(0, diff(confirmed)),
      new_ma = sma(new, n)
    ) %>%
    dplyr::filter(confirmed > 0, !is.na(new_ma)) %>%
    mutate(
      R = c(NA, new_ma[-1] / new_ma[-n()]),
      R = case_when(
        is.nan(R) ~ NA_real_,
        !is.nan(R) ~ R
      ),
      State = "All States"
    ) %>%
    arrange(State)
) %>%
  bind_rows() %>%
  dplyr::filter(date > ymd("2020-03-15")) %>%
  ggplot(aes(date, R, colour = State)) +
  geom_ribbon(aes(ymin = 1, ymax = R), alpha = 0.1) +
  geom_hline(yintercept = 1) +
  geom_vline(
    xintercept = ymd("2020-03-22"),
    linetype = 2,
    colour = "grey30"
  ) +
  geom_label(
    aes(label = R),
    data = . %>%
      dplyr::filter(date == max(date)) %>%
      mutate(R = round(R, 2), date = date + 1),
    fill = rgb(1, 1, 1, 0.3),
    show.legend = FALSE,
    nudge_y = 0.3,
    size = 4
  ) +
  labs(
    x = "Date", y = "Growth Factor"
  ) +
  facet_wrap(~State, scales = "free_x") +
  theme(legend.position = "none") +
  coord_cartesian(ylim = c(0.4, 2.1))
gf

Growth factor for each State/Territory. This value becomes volatile when daily new cases approach zero as is commonly observed in small populations, and at the end stages of an outbreak. Given the multiple updates during the course of the day, values shown represent those up to the previous day. In order to try and minimise volatility a 14 day simple moving average was used, in contrast to the 5 day average as advocated here. This enables assessment of the growth factor over an entire quarantine period. If no new cases are observed over this period, the value is not able to be calculated. The dashed vertical lines indicate the day most state borders were closed.

The current 14 day growth factor is 1.2 which gives considerable cause for concern..

Testing Within Each State

tested %>% 
  left_join(confirmed, by = c("State", "Country", "date") ) %>%
  dplyr::filter(date == dt) %>%
  left_join(ausPops,  by = "State") %>%
  bind_rows(
    tibble(
      State = "National Total",
      date = dt,
      Population = sum(.$Population, na.rm = TRUE),
      confirmed = sum(.$confirmed, na.rm = TRUE),
      tests = sum(.$tests, na.rm = TRUE)
    )
  ) %>%
  mutate(
    `Tests / '000` = round(1e3 * tests / Population, 2),
    Positive = confirmed / tests,
    Negative = 1 - Positive,
    isTotal = grepl("Total", State)
  ) %>%
  dplyr::select(
    State, Population,
    Confirmed = confirmed,
    Tests = tests, 
    contains("000"), 
    ends_with("ive"),
    isTotal
  ) %>%
  arrange(isTotal, desc(`Tests / '000`)) %>%
  dplyr::select(-isTotal) %>%
  dplyr::rename(
    `% Positive Tests` = Positive,
    `% Negative Tests` = Negative
  ) %>%
  mutate_at(
    vars(starts_with("%")), percent, accuracy = 0.01
  ) %>%
  pander(
    justify = "lrrrrrr",
    missing = "",
    caption = glue(
      "*COVID-19 testing scaled by state population size.
      Confirmed cases are assumed to be the tests returning a positive result.
      The current numbers available for some states are a lower limit, and as such, the proportion of the population tested is likely to be higher, as is the proportion of tests returning a negative result.*"
    ),
    emphasize.strong.rows = nrow(.)
  )

COVID-19 testing scaled by state population size. Confirmed cases are assumed to be the tests returning a positive result. The current numbers available for some states are a lower limit, and as such, the proportion of the population tested is likely to be higher, as is the proportion of tests returning a negative result.

State	Population	Confirmed	Tests	Tests / ’000	% Positive Tests	% Negative Tests
Victoria	6,629,870	20,357	3,761,398	567.3	0.54%	99.46%
New South Wales	8,117,976	4,771	3,731,325	459.6	0.13%	99.87%
South Australia	1,756,494	566	784,984	446.9	0.07%	99.93%
Northern Territory	245,562	71	77,941	317.4	0.09%	99.91%
Australian Capital Territory	428,060	118	129,886	303.4	0.09%	99.91%
Queensland	5,115,451	1,235	1,421,147	277.8	0.09%	99.91%
Tasmania	535,500	234	137,693	257.1	0.17%	99.83%
Western Australia	2,630,557	846	606,280	230.5	0.14%	99.86%
National Total	25,459,470	28,198	10,650,654	418.3	0.26%	99.74%

R Session Information

R version 4.0.3 (2020-10-10)

Platform: x86_64-pc-linux-gnu (64-bit)

locale: LC_CTYPE=C, LC_NUMERIC=C, LC_TIME=C, LC_COLLATE=C, LC_MONETARY=C, LC_MESSAGES=en_AU.UTF-8, LC_PAPER=en_AU.UTF-8, LC_NAME=C, LC_ADDRESS=C, LC_TELEPHONE=C, LC_MEASUREMENT=en_AU.UTF-8 and LC_IDENTIFICATION=C

attached base packages: stats, graphics, grDevices, utils, datasets, methods and base

other attached packages: httr(v.1.4.2), readxl(v.1.3.1), ggfortify(v.0.4.11), QuantTools(v.0.5.7.1), data.table(v.1.13.4), cowplot(v.1.1.0), plotly(v.4.9.2.1), pander(v.0.6.3), RCurl(v.1.98-1.2), rvest(v.0.3.6), xml2(v.1.3.2), jsonlite(v.1.7.2), glue(v.1.4.2), broom(v.0.7.2), ggrepel(v.0.8.2), matrixStats(v.0.57.0), scales(v.1.1.1), lubridate(v.1.7.9.2), magrittr(v.2.0.1), forcats(v.0.5.0), stringr(v.1.4.0), dplyr(v.1.0.2), purrr(v.0.3.4), readr(v.1.4.0), tidyr(v.1.1.2), tibble(v.3.0.4), ggplot2(v.3.3.2) and tidyverse(v.1.3.0)

loaded via a namespace (and not attached): Rcpp(v.1.0.5), assertthat(v.0.2.1), digest(v.0.6.27), R6(v.2.5.0), cellranger(v.1.1.0), backports(v.1.2.1), reprex(v.0.3.0), evaluate(v.0.14), highr(v.0.8), pillar(v.1.4.7), rlang(v.0.4.9), curl(v.4.3), lazyeval(v.0.2.2), rstudioapi(v.0.13), rmarkdown(v.2.5), labeling(v.0.4.2), selectr(v.0.4-2), htmlwidgets(v.1.5.3), munsell(v.0.5.0), compiler(v.4.0.3), modelr(v.0.1.8), xfun(v.0.19), pkgconfig(v.2.0.3), htmltools(v.0.5.0), tidyselect(v.1.1.0), gridExtra(v.2.3), fasttime(v.1.0-2), fansi(v.0.4.1), viridisLite(v.0.3.0), crayon(v.1.3.4), dbplyr(v.2.0.0), withr(v.2.3.0), bitops(v.1.0-6), grid(v.4.0.3), gtable(v.0.3.0), lifecycle(v.0.2.0), DBI(v.1.1.0), cli(v.2.2.0), stringi(v.1.5.3), farver(v.2.0.3), fs(v.1.5.0), ellipsis(v.0.3.1), generics(v.0.1.0), vctrs(v.0.3.5), Cairo(v.1.5-12.2), tools(v.4.0.3), crosstalk(v.1.1.0.1), hms(v.0.5.3), yaml(v.2.2.1), colorspace(v.2.0-0), knitr(v.1.30) and haven(v.2.3.1)